Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5129 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0605. Min Act: -0.0001

Data Index: 657541 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0598. Min Act: -0.0001

Data Index: 135856 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0554. Min Act: -0.0001

Data Index: 1302815 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0557. Min Act: -0.0001

Data Index: 172112 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0558. Min Act: -0.0001

Data Index: 609545 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0550. Min Act: -0.0001

Data Index: 1273307 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0554. Min Act: -0.0001

Data Index: 1239796 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0551. Min Act: -0.0001

Data Index: 224768 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0535. Min Act: -0.0001

Data Index: 807304 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0526. Min Act: -0.0001

Data Index: 564052 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0525. Min Act: -0.0002

Data Index: 52468 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0533. Min Act: -0.0001

Data Index: 1237016 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0517. Min Act: -0.0001

Data Index: 13413 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0502. Min Act: -0.0001

Data Index: 325182 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0526. Min Act: -0.0001

Data Index: 1038776 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0498. Min Act: -0.0001

Data Index: 1233112 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0503. Min Act: -0.0001

Data Index: 193745 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0494. Min Act: -0.0001

Data Index: 808008 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0502. Min Act: -0.0001

Data Index: 497968 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0495. Min Act: -0.0001

Data Index: 225284 (C4 (Web Text))

Max Activating Token Index: 67